Journal article
Pediatric Long COVID Subphenotypes: An EHR-based study from the RECOVER program
PLOS digital health, Vol.4(4), e0000747
04/2025
DOI: 10.1371/journal.pdig.0000747
PMCID: PMC11984710
PMID: 40208885
Abstract
Pediatric Long COVID has been associated with a wide variety of symptoms, conditions, and organ systems, but distinct clinical presentations, or subphenotypes, are still being elucidated. In this exploratory analysis, we identified a cohort of pediatric (age <21) patients with evidence of Long COVID and no pre-existing complex chronic conditions using electronic health record data from 38 institutions and used an unsupervised machine learning-based approach to identify subphenotypes. Our method, an extension of the Phe2Vec algorithm, uses tens of thousands of clinical concepts from multiple domains to represent patients' clinical histories to then identify groups of patients with similar presentations. The results indicate that cardiorespiratory presentations are most common (present in 54% of patients) followed by subphenotypes marked (in decreasing order of frequency) by musculoskeletal pain, neuropsychiatric conditions, gastrointestinal symptoms, headache, and fatigue.
Details
- Title: Subtitle
- Pediatric Long COVID Subphenotypes: An EHR-based study from the RECOVER program
- Creators
- Vitaly Lorman - Children's Hospital of PhiladelphiaL Charles Bailey - Children's Hospital of PhiladelphiaXing Song - University of MissouriSuchitra Rao - Children's Hospital ColoradoMady Hornig - Columbia UniversityLevon Utidjian - Children's Hospital of PhiladelphiaHanieh Razzaghi - Children's Hospital of PhiladelphiaAsuncion Mejias - St. Jude Children's Research HospitalJohn Erik Leikauf - Stanford University School of MedicineSeuli Bose Brill - The Ohio State UniversityAndrea Allen - Children's Hospital of PhiladelphiaH Timothy Bunnell - Biomedical Research Informatics Center, Nemours Children's Health, Wilmington, Delaware, United States of AmericaCara Reedy - Biomedical Research Informatics Center, Nemours Children's Health, Wilmington, Delaware, United States of AmericaAbu Saleh Mohammad Mosa - University of MissouriBenjamin D Horne - Intermountain Medical CenterCarol Reynolds Geary - University of Nebraska Medical CenterCynthia H Chuang - Pennsylvania State UniversityDavid A Williams - University of MichiganDimitri A Christakis - Center for Child Health, Behavior and Development, Seattle Children's Research Institute, Seattle, Washington, United States of AmericaElizabeth A Chrischilles - University of IowaEneida A Mendonca - Cincinnati Children's Hospital Medical CenterLindsay G Cowell - The University of Texas Southwestern Medical CenterLisa McCorkell - Columbia UniversityMei Liu - Department of Health Outcomes and Biomedical Informatics, College of Medicine University of Florida, Gainesville, Florida, United States of AmericaMollie R Cummins - University of UtahRavi Jhaveri - Lurie Children's HospitalSaul Blecker - New York UniversityChristopher B Forrest - Children's Hospital of PhiladelphiaResearching COVID to Enhance Recovery (RECOVER) Consortium
- Resource Type
- Journal article
- Publication Details
- PLOS digital health, Vol.4(4), e0000747
- DOI
- 10.1371/journal.pdig.0000747
- PMID
- 40208885
- PMCID
- PMC11984710
- NLM abbreviation
- PLOS Digit Health
- ISSN
- 2767-3170
- eISSN
- 2767-3170
- Publisher
- PUBLIC LIBRARY SCIENCE; SAN FRANCISCO
- Grant note
- National Institute of HealthNIH Researching COVID to Enhance Recovery (RECOVER) Initiative
This study is part of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative, which seeks to understand, treat, and prevent the post-acute sequelae of SARS-CoV-2 infection (PASC). For more information on RECOVER, visit https://recovercovid.org/
- Language
- English
- Date published
- 04/2025
- Academic Unit
- Pharmacy; Epidemiology
- Record Identifier
- 9984808283102771
Metrics
4 Record Views